1,721,139 research outputs found
Recurrent neural networks can learn simple, approximate regular languages
No full textA number of researchers have shown that discrete-time recurrent neural networks (DTRNN) are capable of inferring deterministic finite automata from sets of example and counterexample strings; however, discrete algorithmic methods are much better at this task and clearly outperform DTRNN in terms of space and time complexity. We show how DTRNN may be used to learn not the exact language that explains the whole learning set but an approximate and much simpler language that explains a great majority of the examples by using simpler rules. This is accomplished by gradually varying the error function in such a way that the DTRNN is eventually allowed to classify clearly but incorrectly those strings that it has found to be difficult to learn, which are treated as exceptions. The results show that in this way, the DTRNN usually manages to learn a simplified approximate language
Top-down Transfer in Example-based MT
Get PDFIn this paper we describe and evaluate a top-down transfer component of a hybrid example-based machine translation system with an architecture similar to that of transfer MT systems, but with automatically derived transfer-rules and dictionary entries based on a parallel treebank. The tests
were applied on the translation pair Dutch to English. Evaluation and error analysis have shown that the top-down transfer process has a number of shortcomings on which we wish to report and which we will try to solve in future work by applying bottom-up transfer.sponsorship: AMASS++ project (IWT)/ PaCo-MT project (STE07007)status: Publishe
Making sense of neural machine translation
No full textThe last few years have witnessed a surge in the interest of a new machine translation paradigm: neural machine translation (NMT). Neural machine translation is starting to displace its corpus-based predecessor, statistical machine translation (SMT). In this paper, I introduce NMT, and explain in detail, without the mathematical complexity, how neural machine translation systems work, how they are trained, and their main differences with SMT systems. The paper will try to decipher NMT jargon such as “distributed representations”, “deep learning”, “word embeddings”, “vectors”, “layers”, “weights”, “encoder”, “decoder”, and “attention”, and build upon these concepts, so that individual translators and professionals working for the translation industry as well as students and academics in translation studies can make sense of this new technology and know what to expect from it. Aspects such as how NMT output differs from SMT, and the hardware and software requirements of NMT, both at training time and at run time, on the translation industry, will be discussed.This work was performed while the author was on sabbatical leave at the University of Sheffield and the University of Edinburgh: the author thanks Universitat d’Alacant and the Spanish Ministry of Education, Culture and Sport (grant number PRX16/00043) for support during this leave
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Introducción a la traducción automática
No full textBreve introducción a la traducción automática para estudiantes del Máster en Traducción Instituciona
Free/Open-Source Machine Translation for the Low-Resource Languages of Spain (Invited Talk)
No full textWhile machine translation has historically been rule-based, that is, based on dictionaries and rules written by experts, most present-day machine translation is corpus-based. In the last few years, statistical machine translation, the dominant corpus-based approach, has been displaced by neural machine translation in most applications, in view of the better results reported, particularly for languages with very different syntax. But both statistical and neural machine translation need to be trained on large amounts of parallel data, that is, sentences in one language carefully paired with their translations in their other language, and this is a resource that may not be available for some low-resource languages. While some of the languages of Spain may be considered to be reasonably endowed with parallel corpora connecting them to Spanish or even to English - Basque, Catalan, Galician -, and are well-served with machine translation systems, there are many other languages which cannot afford them such as Aranese Occitan, Aragonese, or Asturian/Leonese. Fortunately, languages in this last group belong to the Romance language family, as Spanish does, and this makes translation from and into Spanish under a rule-based paradigm the only feasible approach. After describing briefly the main machine translation paradigms, I will describe the Apertium free/open-source rule-based machine translation platform, which has been used to build machine translation systems for these low-resource languages of Spain, indeed, sometimes the only ones available. The free/open-source setting has made linguistic data for these languages available for anyone in their linguistic communities to build other linguistic technologies for these low-resourced languages. For example, the Apertium family of bilingual and monolingual data has been converted into RDF and they have been made accessible on the Web as linked data
Building machine translation systems for minor languages: challenges and effects
Get PDFLa creació de sistemes de traducció automàtica per a llengües desfavorides, que anomenaré llengües menors, presenta diversos reptes alhora que obri la porta a noves oportunitats. Després de definir conceptes preliminars com ara els de llengua menor i traducció automàtica, i d’explicar breument els tipus de traducció automàtica existents, els usos més comuns, el tipus de dades en què es basen, i els drets d’ús i les llicències del programari i de les dades de traducció automàtica, es discuteixen els reptes a què s’enfronta la construcció de sistemes de traducció automàtica i els possibles efectes sobre l’estatus de la llengua menor, usant com a exemples llengües menors d’Europa.Building machine translation systems for disadvantaged languages, which I will call minor languages, poses a number of challenges whilst also opening the door to new opportunities. After defining a few basic concepts, such as minor language and machine translation, the paper provides a brief overview of the types of machine translation available today, their most common uses, the type of data they are based on, and the usage rights and licences of machine translation software and data. Then, it describes the challenges involved in building machine translation systems, as well as the effects these systems can have on the status of minor languages. Finally, this is illustrated by drawing on examples from minor languages in Europe
Com funcionen els models massius de llengua de l'estil de ChatGPT?
No full textUna de les manifestacions més importants de l'anomenada ”intel·ligència artificial” són els models massius de llengua (MML), models que, en resposta a un text d'entrada, prediuen possibles continuacions o respostes. En particular, models com ChatGPT o Google Bard, disponibles públicament, són capaços de mantenir “converses” en les quals generen respostes que poden ser percebudes com a “intel·ligents“ en resposta a les intervencions de la persona usuària: per això, hi ha qui en diu “intel·ligència artificial generativa“. Aquestes capacitats tenen un gran impacte en tots els sectors professionals on la generació de textos és una activitat clau. En aquesta xarrada, intentaré explicar en termes accessibles a una audiència no tècnica el funcionament intern i l'entrenament dels models massius de llengua. La intenció es contribuir a un apoderament tecnològic de qui els usa, perquè comprenga els efectes d'aquesta tecnologia disruptiva i prendre decisions més informades a l'hora d'usar-lo
- …
